{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O2GKCIJPIORMBIHL4E6OL3T7JS","short_pith_number":"pith:O2GKCIJP","schema_version":"1.0","canonical_sha256":"768ca1212f43a2c0a0ebe13ce5ee7f4c84dff0dd5d43f18b723b36d5cf964722","source":{"kind":"arxiv","id":"2104.05596","version":4},"attestation_state":"computed","paper":{"title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ajitesh Sharma, Anoop Kunchukuttan, Aravinth Bheemaraj, Aswin Pradeep, Divyanshu Kakwani, Gowtham Ramesh, Harshita Diddee, Kumar Deepak, Mahalakshmi J, Mayank Jobanputra, Mitesh Shantadevi Khapra, Navneet Kumar, Pratyush Kumar, Raghavan AK, Srihari Nagaraj, Sujit Sahoo, Sumanth Doddapaneni, Vivek Raghavan","submitted_at":"2021-04-12T16:18:20Z","abstract_excerpt":"We present Samanantar, the largest publicly available parallel corpora collection for Indic languages. The collection contains a total of 49.7 million sentence pairs between English and 11 Indic languages (from two language families). Specifically, we compile 12.4 million sentence pairs from existing, publicly-available parallel corpora, and additionally mine 37.4 million sentence pairs from the web, resulting in a 4x increase. We mine the parallel sentences from the web by combining many corpora, tools, and methods: (a) web-crawled monolingual corpora, (b) document OCR for extracting sentence"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2104.05596","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T16:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"85768bbb82b2f86bf930865e74cd1412fda823938f599d751342242624c09873","abstract_canon_sha256":"f8852c9db6816f235cf0e3afb82218db1dbae22c7ece0f4f13947c7c9cf31639"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:50.426019Z","signature_b64":"0nyHqpPCWz/lDsYqnMxzBDeq8RIU1NHAkBD4TzuYpaa1G2l7ku2Mk68z0se0EH+j3VeQ6Dz5V5sNZ0i0qao6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"768ca1212f43a2c0a0ebe13ce5ee7f4c84dff0dd5d43f18b723b36d5cf964722","last_reissued_at":"2026-07-05T06:19:50.425469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:50.425469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ajitesh Sharma, Anoop Kunchukuttan, Aravinth Bheemaraj, Aswin Pradeep, Divyanshu Kakwani, Gowtham Ramesh, Harshita Diddee, Kumar Deepak, Mahalakshmi J, Mayank Jobanputra, Mitesh Shantadevi Khapra, Navneet Kumar, Pratyush Kumar, Raghavan AK, Srihari Nagaraj, Sujit Sahoo, Sumanth Doddapaneni, Vivek Raghavan","submitted_at":"2021-04-12T16:18:20Z","abstract_excerpt":"We present Samanantar, the largest publicly available parallel corpora collection for Indic languages. The collection contains a total of 49.7 million sentence pairs between English and 11 Indic languages (from two language families). Specifically, we compile 12.4 million sentence pairs from existing, publicly-available parallel corpora, and additionally mine 37.4 million sentence pairs from the web, resulting in a 4x increase. We mine the parallel sentences from the web by combining many corpora, tools, and methods: (a) web-crawled monolingual corpora, (b) document OCR for extracting sentence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05596","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.05596/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.05596","created_at":"2026-07-05T06:19:50.425542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05596v4","created_at":"2026-07-05T06:19:50.425542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05596","created_at":"2026-07-05T06:19:50.425542+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2GKCIJPIORM","created_at":"2026-07-05T06:19:50.425542+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2GKCIJPIORMBIHL","created_at":"2026-07-05T06:19:50.425542+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2GKCIJP","created_at":"2026-07-05T06:19:50.425542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29379","citing_title":"BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2GKCIJPIORMBIHL4E6OL3T7JS","json":"https://pith.science/pith/O2GKCIJPIORMBIHL4E6OL3T7JS.json","graph_json":"https://pith.science/api/pith-number/O2GKCIJPIORMBIHL4E6OL3T7JS/graph.json","events_json":"https://pith.science/api/pith-number/O2GKCIJPIORMBIHL4E6OL3T7JS/events.json","paper":"https://pith.science/paper/O2GKCIJP"},"agent_actions":{"view_html":"https://pith.science/pith/O2GKCIJPIORMBIHL4E6OL3T7JS","download_json":"https://pith.science/pith/O2GKCIJPIORMBIHL4E6OL3T7JS.json","view_paper":"https://pith.science/paper/O2GKCIJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05596&json=true","fetch_graph":"https://pith.science/api/pith-number/O2GKCIJPIORMBIHL4E6OL3T7JS/graph.json","fetch_events":"https://pith.science/api/pith-number/O2GKCIJPIORMBIHL4E6OL3T7JS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2GKCIJPIORMBIHL4E6OL3T7JS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2GKCIJPIORMBIHL4E6OL3T7JS/action/storage_attestation","attest_author":"https://pith.science/pith/O2GKCIJPIORMBIHL4E6OL3T7JS/action/author_attestation","sign_citation":"https://pith.science/pith/O2GKCIJPIORMBIHL4E6OL3T7JS/action/citation_signature","submit_replication":"https://pith.science/pith/O2GKCIJPIORMBIHL4E6OL3T7JS/action/replication_record"}},"created_at":"2026-07-05T06:19:50.425542+00:00","updated_at":"2026-07-05T06:19:50.425542+00:00"}